ML/Data Engineer

About the role

Build production data infrastructure for athlete performance and sensor data, supporting machine learning and AI systems. The role involves streaming ingestion, time-series storage and graph data models for a sports technology customer.

What you will do

• Design storage and data architectures for time-series data and longitudinal athlete records
• Create graph data models and schemas linking athletes, training loads, injuries and outcomes
• Build data and ML evaluation infrastructure measuring model reliability, calibration and performance
• Ensure tenant-level data isolation, provenance, lineage, auditability and observability

What they look for

• Proven experience designing and operating production data infrastructure at scale
• Strong time-series data or database experience, such as InfluxDB, TimescaleDB, Prometheus or ClickHouse
• Significant streaming ingestion experience with Kafka, Kinesis, Flink, Spark Streaming or Pulsar
• Strong Python and SQL skills

Nice to have

• Professional Go experience
• Probabilistic evaluation, model calibration or model monitoring infrastructure
• Causal inference, counterfactual modelling or simulation
• Wearable sensors, IoT, biomechanics or sports technology telemetry